🔌
New: connect Claude & other AIs to GenAIList over MCP — research the catalog and contribute to the shared knowledge base. Learn how →
// RUN — FITS
Can the Instinct MI430X run GPT-Neo-125M?
Yes — here's how fast and up to what context, with real measured numbers.
GPT-Neo-125M on the Instinct MI430X
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 6038k | 58716-71764 t/s | ~100.8-123.2 (slow) |
| Q8 | yes | 6040k | 117432-143528 t/s | ~201.6-246.4 (slow) |
| Q4 | yes | 6040k | 209700-256300 t/s | ~360-440 (slow) |
Estimate (memory-bound). Beyond "max context" the KV cache spills to system RAM offload (depends on your system RAM) and speed drops to the "beyond" figure.
FAQ
Can the Instinct MI430X run GPT-Neo-125M?▶
Yes. At Q4 it generates ~209700-256300 tok/s and fits up to 6040k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~360-440 tok/s.
How much context fits?▶
At Q4, up to about 6040k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.